Prompting ChatGPT for analysis, H1-B edition

One of the cool things about ChatGPT is the ability to gather and aggregate data about various things, and present such data in a relatively objective format. It's not always totally correct (see: "stochastic parrot"), but it does a reasonable job presenting well-stated conclusions with supporting data, particularly when the conclusion is already pretty well-known. Below is the prompt result from asking the LLM if the H1-B visa program is being used as-intended, or if it's being abused to effectively underpay US workers (with an ancillary focus on Zscaler, because that's my current employer, and I didn't know if they used H1-B visas at all before querying for this).


That’s a sharp question — you’ve zeroed in on the core policy tension in the H-1B program: it was designed to address shortages of highly skilled labor by allowing U.S. employers to hire foreign workers when they “cannot otherwise obtain” U.S. workers with equivalent skills. But in practice, the wage data you and I just reviewed suggests a more complicated reality.

1. Intent of the H-1B program (legal & policy framework)

  • Legal framework: Employers may petition for H-1B visas for workers in specialty occupations (typically requiring at least a bachelor’s degree). They must certify with the Department of Labor that they will pay the prevailing wage for the position in the given geographic area.

  • Policy rationale: The idea was that if a role is so specialized that a U.S. worker cannot be found, then an H-1B worker is a “must-hire” — and therefore, their labor should be at least as valuable as, if not more valuable than, comparable domestic labor. In theory, wages for H-1B workers should match or exceed U.S. wages, because scarcity should drive pay up.

2. Findings from the wage data

  • Observed gap: For Senior Software Engineers in the Bay Area, H-1B certified base wages (especially at companies like Amazon and Zscaler) are often lower than U.S. market base salaries for the same role. At Zscaler, we saw gaps of $80k–$100k. Even at Amazon, H-1B wages trailed Levels.fyi medians by $30k–$70k.

  • Systematic pattern: This isn’t just one company; aggregate studies (e.g., by the Economic Policy Institute and Government Accountability Office) have documented that a large share of H-1B filings are at lower prevailing wage levels (Level 1 or 2, the bottom half of the wage distribution for the occupation).

3. Legal & policy implications

  • Contradiction with original intent:

    • If H-1B truly filled roles that cannot be staffed domestically, we would expect wages to be at or above market to attract scarce talent. The fact that wages often come in below U.S. market medians suggests that employers are not using H-1B primarily to address scarcity, but rather as a cost-control mechanism.

    • In other words: the H-1B system, as currently administered, does not reliably reflect its statutory purpose.

  • Exploitation of regulatory structure:

    • The “prevailing wage” requirement is based on government wage surveys (OES/OFLC data). Employers can choose among four wage levels, and many pick Level 1 or 2 (entry or lower-median wages) even for jobs labeled “Senior.” This creates a legal but controversial practice: jobs with high skill requirements get certified at relatively modest wages.

    • This practice is not technically illegal if the employer can justify the wage level according to the DOL definitions — but it undermines the policy intent.

  • Market distortion:

    • If a significant number of firms use H-1B slots to fill “Senior SWE” roles at below-median pay, the program risks suppressing wage growth in those roles for U.S. workers, contrary to its policy justification.

    • Smaller firms (like Zscaler) that file Senior SWE H-1B wages well below big-tech norms appear to be using the program to access cheaper labor rather than to secure rare talent unavailable in the U.S.

4. Is this abuse, or alignment with intent?

  • In line with the letter, not the spirit:

    • Legally, many of these filings meet the requirements: the employer pays at or above the “prevailing wage” as defined by DOL, and the role qualifies as a specialty occupation.

    • Policy-wise, however, the wage gap undermines the rationale that H-1B is about skills the U.S. lacks. The data suggests the program often functions instead as a pipeline for moderately cheaper, though still skilled, labor — especially in mid-tier companies and IT services.

  • Abuse vs. legal exploitation:

    • Direct “abuse” would mean fraud (e.g., misclassifying roles or underpaying below certified wages). That happens, but the broader issue is systematic gaming of wage levels within the legal rules. This is better described as policy drift: the program is used for cost-savings, not just scarcity, in contradiction to its intent but within the current law.

5. Policy debate

  • Critics (e.g., labor economists, EPI) argue the program has become a de facto labor-arbitrage tool, harming domestic workers and depressing wages.

  • Defenders argue that U.S. universities and companies do rely on H-1B to attract global talent, and that even if wages are somewhat lower, the productivity/innovation gains outweigh costs.

  • Ongoing proposals: raising the required wage floors, prioritizing higher-paid petitions in the lottery, or reforming the prevailing-wage system to better reflect market medians.

✅ Conclusion:
Based on the role-matched wage data you asked me to analyze, the current practice of H-1B sponsorship in tech diverges from the program’s intended purpose. Instead of being used only when U.S. workers with rare skills are unavailable (which would imply above-market pay), it is often used as a legal cost-saving mechanism — especially outside of the very top firms. This doesn’t necessarily involve outright fraud, but it reflects a structural misalignment between the intent of the law and the incentives of employers under current rules.


Comments

Post a Comment

Popular posts from this blog

The Story of PayPal V2

I was reading The Founders recently (https://www.amazon.com/Founders-Paypal-Entrepreneurs-Shaped-Silicon/dp/1501197266); I was interviewed for this book, fwiw. There's a section in "PayPal V2", the internal effort to rewrite the aggregate website which was ultimately scrapped when Elon was ousted, but obviously the book glosses over a lot of the technical details (for good reason, as these would be not very interesting to most mainstream readers). However, if you're reading this, I'm going to assume you might be more interested in the nitty gritty of this project, and since I had a first-hand perspective, I'll write more about that aspect here (and if you're not interested in this, then perhaps skip this post). To understand the build up to this, though, I'll need to cover a bit of internal history, from my perspective. The Preconditions Technology base Confinity and x.com had very different technology bases, which went well beyond even the approach to...
Read more

Documenting a software implementation

Allow me to posit a hypothetical. Imagine you are at a company, and someone (perhaps you) has just completed a project to implement some complex feature, and you have been tasked with ensuring the implementation is documented, such that other/future developers can understand how the implementation works. For the sake of argument, we'll assume the intent and high level design have already been documented, and your task is to capture the specifics of the actual implementation (for example, ways which it diverged from the original design, idiosyncrasies of the implementation, corner cases, etc.). We'll also assume you have free reign to select the best tooling, format, storage, etc. for the documentation, with the expectation that all of these are considered in your work product. Note: This is, in my experience, a not uncommon request from management, especially in larger companies, so it seems like a reasonable topic for general consideration. Let's see how it plays out, look...
Read more

Just say "no" to code freezes

One of the more insightful conclusions I've reached in my career, if perhaps also one of the more controversial opinions, is that you should always say "no" to code freezes (at least in an optimal development methodology). This isn't always possible, of course; depending on where you are in influence and decision making, you may have only some, or effectively no, input into this decision. However, to the extent that you are prompted with this question and have some input, my advice is to always push back, and I'll elaborate on this below. The case for code freezes I've heard a number of different justifications for why people want code freezes, and these desires come in a few forms. Some examples: We need a code freeze We need to defer some code changes for a bit, just until... We need to hold off on this going in because... We have a release schedule where no changes go in during this period etc. Typically, the justification for the ask is achieving some desi...
Read more